{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2PSRDSTLMEYY34V62X6JEUSNCN","short_pith_number":"pith:2PSRDSTL","canonical_record":{"source":{"id":"2203.01387","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"708424bdddc8fc2cd197a33d3c42d13011f0ee801c57887bf38972ec9006d776","abstract_canon_sha256":"697d3b3cba32242dc2241d79b06130c731ec97df2c5e4fd58d00f9eb8e3f46df"},"schema_version":"1.0"},"canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","source":{"kind":"arxiv","id":"2203.01387","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.01387","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2203.01387v3","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01387","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"2PSRDSTLMEYY","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"2PSRDSTLMEYY34V6","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"2PSRDSTL","created_at":"2026-07-05T06:02:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2PSRDSTLMEYY34V62X6JEUSNCN","target":"record","payload":{"canonical_record":{"source":{"id":"2203.01387","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"708424bdddc8fc2cd197a33d3c42d13011f0ee801c57887bf38972ec9006d776","abstract_canon_sha256":"697d3b3cba32242dc2241d79b06130c731ec97df2c5e4fd58d00f9eb8e3f46df"},"schema_version":"1.0"},"canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:27.580844Z","signature_b64":"FJ/hIiIhF/LvWjpBT24R30i9CvOLmKJSHJuZJ+Jkas7WgYcjh8VBK7xJb3iba2Du0mbNYI5T0TKUnDTD/q0VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","last_reissued_at":"2026-07-05T06:02:27.580469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:27.580469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.01387","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:02:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dS8qk2fqNDM0BomfGguFeiteWz6pPyI8TtOJN+QKBSMBVUlOY2TBGrVmG6lIY7+8iAt32Q34sL9lYpAIaKBNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:04:37.396449Z"},"content_sha256":"4f761906984640b2db1a32c2e48294d701694099498be5a75de7aed73bf02997","schema_version":"1.0","event_id":"sha256:4f761906984640b2db1a32c2e48294d701694099498be5a75de7aed73bf02997"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2PSRDSTLMEYY34V62X6JEUSNCN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Esther Luna Colombini, Marcos R. O. A. Maximo, Rafael Figueiredo Prudencio","submitted_at":"2022-03-02T20:05:11Z","abstract_excerpt":"With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games from pixel observations, sustaining conversations with humans, and controlling robotic agents. However, there is still a wide range of domains inaccessible to RL due to the high cost and danger of interacting with the environment. Offline RL is a paradigm that learns exclusively from static datasets of previously collected interactions, making it feasible to extract policies from large and diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01387","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.01387/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:02:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+RvyhOHQ2T3Er3djh/rRSYJO5Zmy1rdGYo+sWOSPUnQ2M0jVAD/IQ4yMWu+w2P4WD9LsfJaCJ935xjy9PnNXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:04:37.397387Z"},"content_sha256":"9ce00e950d74dd04ab30fb3026c27fa5b7fd4d4037f97a127e9fabb9dc821838","schema_version":"1.0","event_id":"sha256:9ce00e950d74dd04ab30fb3026c27fa5b7fd4d4037f97a127e9fabb9dc821838"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/bundle.json","state_url":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PSRDSTLMEYY34V62X6JEUSNCN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T04:04:37Z","links":{"resolver":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN","bundle":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/bundle.json","state":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PSRDSTLMEYY34V62X6JEUSNCN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2PSRDSTLMEYY34V62X6JEUSNCN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"697d3b3cba32242dc2241d79b06130c731ec97df2c5e4fd58d00f9eb8e3f46df","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","title_canon_sha256":"708424bdddc8fc2cd197a33d3c42d13011f0ee801c57887bf38972ec9006d776"},"schema_version":"1.0","source":{"id":"2203.01387","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.01387","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2203.01387v3","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01387","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"2PSRDSTLMEYY","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"2PSRDSTLMEYY34V6","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"2PSRDSTL","created_at":"2026-07-05T06:02:27Z"}],"graph_snapshots":[{"event_id":"sha256:9ce00e950d74dd04ab30fb3026c27fa5b7fd4d4037f97a127e9fabb9dc821838","target":"graph","created_at":"2026-07-05T06:02:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.01387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games from pixel observations, sustaining conversations with humans, and controlling robotic agents. However, there is still a wide range of domains inaccessible to RL due to the high cost and danger of interacting with the environment. Offline RL is a paradigm that learns exclusively from static datasets of previously collected interactions, making it feasible to extract policies from large and diverse","authors_text":"Esther Luna Colombini, Marcos R. O. A. Maximo, Rafael Figueiredo Prudencio","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01387","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4f761906984640b2db1a32c2e48294d701694099498be5a75de7aed73bf02997","target":"record","created_at":"2026-07-05T06:02:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"697d3b3cba32242dc2241d79b06130c731ec97df2c5e4fd58d00f9eb8e3f46df","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","title_canon_sha256":"708424bdddc8fc2cd197a33d3c42d13011f0ee801c57887bf38972ec9006d776"},"schema_version":"1.0","source":{"id":"2203.01387","kind":"arxiv","version":3}},"canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","first_computed_at":"2026-07-05T06:02:27.580469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:27.580469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FJ/hIiIhF/LvWjpBT24R30i9CvOLmKJSHJuZJ+Jkas7WgYcjh8VBK7xJb3iba2Du0mbNYI5T0TKUnDTD/q0VBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:27.580844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.01387","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f761906984640b2db1a32c2e48294d701694099498be5a75de7aed73bf02997","sha256:9ce00e950d74dd04ab30fb3026c27fa5b7fd4d4037f97a127e9fabb9dc821838"],"state_sha256":"96f30d565bc5d26c63287022b4a8aa37706ae3da0d914b808ec4aaadb74cefc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oeV0Vw2ZhWss49blCC5AVeqrAccgsqoy3gcrDNz1yoXJPg8C2K6ClUFjAP3iJGdnXqyfYe+0rXCM+zJFK7w0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:04:37.404631Z","bundle_sha256":"e7d385f35f6179162bc097d725aa95d86dde8423f7f1f0663ddd3e495a3111c4"}}